© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69901
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -2.33
     Then
    -2.17
     in
    -2.13
     novin
    -2.11
     estar
    -2.03
     інші
    -2.02
     autre
    -1.98
    柃
    -1.97
     белая
    -1.88
     altre
    -1.88
    POSITIVE LOGITS
    的
    3.45
    ed
    2.56
    ’
    2.42
    e
    2.39
     faſt
    2.22
    "
    2.13
    your
    2.09
    8
    2.06
    which
    2.06
    ться
    2.06
    Activations Density 0.001%

    No Known Activations